Files
clang-p2996/llvm/test/CodeGen/AMDGPU/extract_vector_elt-f64.ll
Matt Arsenault 7aad8fd8f4 Enable FeatureFlatForGlobal on Volcanic Islands
This switches to the workaround that HSA defaults to
for the mesa path.

This should be applied to the 4.0 branch.

Patch by Vedran Miletić <vedran@miletic.net>

llvm-svn: 292982
2017-01-24 22:02:15 +00:00

30 lines
1.2 KiB
LLVM

; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
; GCN-LABEL: {{^}}extract_vector_elt_v3f64_2:
; GCN: buffer_load_dwordx4
; GCN: buffer_load_dwordx2
; GCN: buffer_store_dwordx2
define void @extract_vector_elt_v3f64_2(double addrspace(1)* %out, <3 x double> addrspace(1)* %in) #0 {
%ld = load volatile <3 x double>, <3 x double> addrspace(1)* %in
%elt = extractelement <3 x double> %ld, i32 2
store volatile double %elt, double addrspace(1)* %out
ret void
}
; GCN-LABEL: {{^}}dyn_extract_vector_elt_v3f64:
define void @dyn_extract_vector_elt_v3f64(double addrspace(1)* %out, <3 x double> %foo, i32 %elt) #0 {
%dynelt = extractelement <3 x double> %foo, i32 %elt
store volatile double %dynelt, double addrspace(1)* %out
ret void
}
; GCN-LABEL: {{^}}dyn_extract_vector_elt_v4f64:
define void @dyn_extract_vector_elt_v4f64(double addrspace(1)* %out, <4 x double> %foo, i32 %elt) #0 {
%dynelt = extractelement <4 x double> %foo, i32 %elt
store volatile double %dynelt, double addrspace(1)* %out
ret void
}
attributes #0 = { nounwind }